Signal quality measures for unsupervised blood pressure measurement.

Accurate systolic and diastolic pressure estimation, using automated blood pressure measurement, is difficult to achieve when the transduced signals are contaminated with noise or interference, such as movement artifact. This study presents an algorithm for automated signal quality assessment in blood pressure measurement by determining the feasibility of accurately detecting systolic and diastolic pressures when corrupted with various levels of movement artifact. The performance of the proposed algorithm is compared to a manually annotated reference scoring (RS). Based on visual representations and audible playback of Korotkoff sounds, the creation of the RS involved two experts identifying sections of the recorded sounds and annotating sections of noise contamination. The experts determined the systolic and diastolic pressure in 100 recorded Korotkoff sound recordings, using a simultaneous electrocardiograph as a reference signal. The recorded Korotkoff sounds were acquired from 25 healthy subjects (16 men and 9 women) with a total of four measurements per subject. Two of these measurements contained purposely induced noise artifact caused by subject movement. Morphological changes in the cuff pressure signal and the width of the Korotkoff pulse were extracted features which were believed to be correlated with the noise presence in the recorded Korotkoff sounds. Verification of reliable Korotkoff pulses was also performed using extracted features from the oscillometric waveform as recorded from the inflatable cuff. The time between an identified noise section and a verified Korotkoff pulse was the key feature used to determine the validity of possible systolic and diastolic pressures in noise contaminated Korotkoff sounds. The performance of the algorithm was assessed based on the ability to: verify if a signal was contaminated with any noise; the accuracy, sensitivity and specificity of this noise classification, and the systolic and diastolic pressure differences between the result obtained from the algorithm and the RS. 90% of the actual noise contaminated signals were correctly identified, and a sample-wise accuracy, sensitivity and specificity of 97.0%, 80.61% and 98.16%, respectively, were obtained from 100 pooled signals. The mean systolic and diastolic differences were 0.37 ± 3.31 and 3.10 ± 5.46 mmHg, respectively, when the artifact detection algorithm was utilized, with the algorithm correctly determined if the signal was clean enough to attempt an estimation of systolic or diastolic pressures in 93% of blood pressure measurements.

Signal quality measures for pulse oximetry through waveform morphology analysis.

Pulse oximetry has been extensively used to estimate oxygen saturation in blood, a vital physiological parameter commonly used when monitoring a subject's health status. However, accurate estimation of this parameter is difficult to achieve when the fundamental signal from which it is derived, the photoplethysmograph (PPG), is contaminated with noise artifact induced by movement of the subject or the measurement apparatus. This study presents a novel method for automatic rejection of artifact contaminated pulse oximetry waveforms, based on waveform morphology analysis. The performance of the proposed algorithm is compared to a manually annotated gold standard. The creation of the gold standard involved two experts identifying sections of the PPG signal containing good quality PPG pulses and/or noise, in 104 fingertip PPG signals, using a simultaneous electrocardiograph (ECG) signal as a reference signal. The fingertip PPG signals were each 1 min in duration and were acquired from 13 healthy subjects (10 males and 3 females). Each signal contained approximately 20 s of purposely induced artifact noise from a variety of activities involving subject movement. Some unique waveform morphology features were extracted from the PPG signals, which were believed to be correlated with signal quality. A simple decision-tree classifier was employed to arrive at a classification decision, at a pulse-by-pulse resolution, of whether a pulse was of acceptable quality for use or not. The performance of the algorithm was assessed using Cohen's kappa coefficient (κ), sensitivity, specificity and accuracy measures. A mean κ of 0.64 ± 0.22 was obtained, while the mean sensitivity, specificity and accuracy were 89 ± 10%, 77 ± 19% and 83 ± 11%, respectively. Furthermore, a heart rate estimate, extracted from uncontaminated sections of PPG, as identified by the algorithm, was compared with the heart rate derived from an uncontaminated simultaneous ECG signal. The mean error between both heart rate readings was 0.49 ± 0.66 beats per minute (BPM), in comparison to an error value observed without using the artifact detection algorithm of 7.23 ± 5.78 BPM. These results demonstrate that automated identification of signal artifact in the PPG signal through waveform morphology analysis is achievable. In addition, a clear improvement in the accuracy of the derived heart rate is also evident when such methods are employed.